Distributed Framework for Political Event Coding in Real-Time
Distributed Framework for Political Event Coding in Real-Time
复制标题
实时政治事件编码的分布式框架
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
L. Khan
中科院分区：
文献类型：
--
作者：
S. Salam;Patrick T. Brandt;J. Holmes;L. Khan
研究政治活动和不同实体之间的互动逐渐成为社会科学和计算机科学研究者的一个重要研究领域。目前正在当地（限于某一特定区域）和全球范围内进行研究，通常按时间划分。拥有最新的数据集以进行最新的分析也很有用。出于这些目的，我们需要关于政治互动的带有时间戳的结构化信息。考虑到这一点，我们开发了一个与Apache Kafka和SPARK实时工作的分布式框架，用于处理不同语言（即西班牙语，阿拉伯语）的全球新闻数据集合，并生成这些结构化数据。我们还提供了一个API来方便地访问数据。在本文中，我们将描述系统如何工作，如何访问数据以及可以通过在数据集上构建模型来解决的可能的分析问题。
Studying political activities and interaction between different entities gradually becoming a prominent field of research for both the social science and computer science researchers. Research is being carried out at local (limited to a particular region) and global scale, often divided in temporal manner. It is also useful to have a most recent dataset to have an up-to-date analysis. For these purposes, we need timestamped, structured information about political interactions. Keeping this in mind, we develop a distributed framework that works in real-time with Apache Kafka and SPARK for processing a global collection of news data in different languages (i.e., Spanish, Arabic) and generate those structured data. We also provide a API for easy access to the data. In this paper, we will describe how the system works, how to access the data and possible analytical problems that can be addressed by building a model on the dataset.